INDEX

Explanations

references to death or suicidal actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lenker

-0.45

ագրություններ

-0.44

ionato

-0.43

cento

-0.43

 credit

-0.42

کر

-0.42

otimes

-0.40

 باخ

-0.40

 tortoise

-0.40

 Bever

-0.40

POSITIVE LOGITS

 jumping

1.36

 jump

1.29

 jumped

1.24

 Jump

1.22

 jumps

1.22

 falling

1.19

 fall

1.19

jump

1.16

 Jumping

1.16

Falling

1.16

Activations Density 0.210%

references to death or suicidal actions

No Comments

No Known Activations